End of training

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -11,14 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ner-bert-ingredients
 
-This model was trained from scratch on an unknown dataset.
-It achieves the following results on the evaluation set:
-- eval_loss: 1.3551
-- eval_runtime: 83.7743
-- eval_samples_per_second: 59.684
-- eval_steps_per_second: 0.943
-- epoch: 24.26
-- step: 18000
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 
 ## Model description
 
@@ -45,9 +40,13 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 100
+- num_epochs: 50
 - mixed_precision_training: Native AMP
 
+### Training results
+
+
+
 ### Framework versions
 
 - Transformers 4.36.0

logs/events.out.tfevents.1705980708.70e47a1f5afe.42.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8b895c6bfc5a23bd39e157af13b3392bec37dfddec8b1ed972119675eb7bb83
+size 8429

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fd67a82b1777a8bbb4dcfd6c2bda43327b2e79d9caf192697494fc9ebced34
-size 535667604
+oid sha256:5dbfecedd805a055d558e713fdab59dc3f5ce6a3cc40f43d3abc6ed1ac915a0b
+size 435863700

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -45,18 +45,11 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "max_length": 512,
   "model_max_length": 512,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

trainer_state.json

@@ -1,356 +1,29 @@
 {
-  "best_metric": 1.3392431735992432,
-  "best_model_checkpoint": "ner-bert-ingredients/checkpoint-17250",
-  "epoch": 24.256652071404513,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 50.0,
   "eval_steps": 750,
-  "global_step": 18000,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.01,
-      "learning_rate": 4.949460916442048e-05,
-      "loss": 5.4,
-      "step": 750
-    },
-    {
-      "epoch": 1.01,
-      "eval_loss": 3.985283613204956,
-      "eval_runtime": 84.6074,
-      "eval_samples_per_second": 59.096,
-      "eval_steps_per_second": 0.934,
-      "step": 750
-    },
-    {
-      "epoch": 2.02,
-      "learning_rate": 4.8989218328840976e-05,
-      "loss": 3.3737,
-      "step": 1500
-    },
-    {
-      "epoch": 2.02,
-      "eval_loss": 2.947718858718872,
-      "eval_runtime": 84.1622,
-      "eval_samples_per_second": 59.409,
-      "eval_steps_per_second": 0.939,
-      "step": 1500
-    },
-    {
-      "epoch": 3.03,
-      "learning_rate": 4.84845013477089e-05,
-      "loss": 2.5551,
-      "step": 2250
-    },
-    {
-      "epoch": 3.03,
-      "eval_loss": 2.259490728378296,
-      "eval_runtime": 84.2333,
-      "eval_samples_per_second": 59.359,
-      "eval_steps_per_second": 0.938,
-      "step": 2250
-    },
-    {
-      "epoch": 4.04,
-      "learning_rate": 4.7979110512129385e-05,
-      "loss": 2.0321,
-      "step": 3000
-    },
-    {
-      "epoch": 4.04,
-      "eval_loss": 1.9211012125015259,
-      "eval_runtime": 84.2271,
-      "eval_samples_per_second": 59.363,
-      "eval_steps_per_second": 0.938,
-      "step": 3000
-    },
-    {
-      "epoch": 5.05,
-      "learning_rate": 4.7473719676549865e-05,
-      "loss": 1.6766,
-      "step": 3750
-    },
-    {
-      "epoch": 5.05,
-      "eval_loss": 1.6346299648284912,
-      "eval_runtime": 84.1885,
-      "eval_samples_per_second": 59.391,
-      "eval_steps_per_second": 0.938,
-      "step": 3750
-    },
-    {
-      "epoch": 6.06,
-      "learning_rate": 4.696900269541779e-05,
-      "loss": 1.437,
-      "step": 4500
-    },
-    {
-      "epoch": 6.06,
-      "eval_loss": 1.5281634330749512,
-      "eval_runtime": 84.2371,
-      "eval_samples_per_second": 59.356,
-      "eval_steps_per_second": 0.938,
-      "step": 4500
-    },
-    {
-      "epoch": 7.08,
-      "learning_rate": 4.949460916442048e-05,
-      "loss": 3.7548,
-      "step": 5250
-    },
-    {
-      "epoch": 7.08,
-      "eval_loss": 2.378469228744507,
-      "eval_runtime": 84.0031,
-      "eval_samples_per_second": 59.522,
-      "eval_steps_per_second": 0.94,
-      "step": 5250
-    },
-    {
-      "epoch": 8.09,
-      "learning_rate": 4.8989218328840976e-05,
-      "loss": 1.9326,
-      "step": 6000
-    },
-    {
-      "epoch": 8.09,
-      "eval_loss": 1.8503246307373047,
-      "eval_runtime": 83.659,
-      "eval_samples_per_second": 59.766,
-      "eval_steps_per_second": 0.944,
-      "step": 6000
-    },
-    {
-      "epoch": 9.1,
-      "learning_rate": 4.84845013477089e-05,
-      "loss": 1.489,
-      "step": 6750
-    },
-    {
-      "epoch": 9.1,
-      "eval_loss": 1.630631685256958,
-      "eval_runtime": 83.6797,
-      "eval_samples_per_second": 59.752,
-      "eval_steps_per_second": 0.944,
-      "step": 6750
-    },
-    {
-      "epoch": 10.11,
-      "learning_rate": 4.7979784366576826e-05,
-      "loss": 1.2457,
-      "step": 7500
-    },
-    {
-      "epoch": 10.11,
-      "eval_loss": 1.4776005744934082,
-      "eval_runtime": 83.6823,
-      "eval_samples_per_second": 59.75,
-      "eval_steps_per_second": 0.944,
-      "step": 7500
-    },
-    {
-      "epoch": 11.12,
-      "learning_rate": 4.7474393530997306e-05,
-      "loss": 1.0713,
-      "step": 8250
-    },
-    {
-      "epoch": 11.12,
-      "eval_loss": 1.4048632383346558,
-      "eval_runtime": 83.6632,
-      "eval_samples_per_second": 59.763,
-      "eval_steps_per_second": 0.944,
-      "step": 8250
-    },
-    {
-      "epoch": 12.13,
-      "learning_rate": 4.696900269541779e-05,
-      "loss": 0.9469,
-      "step": 9000
-    },
-    {
-      "epoch": 12.13,
-      "eval_loss": 1.349704384803772,
-      "eval_runtime": 83.6712,
-      "eval_samples_per_second": 59.758,
-      "eval_steps_per_second": 0.944,
-      "step": 9000
-    },
-    {
-      "epoch": 13.14,
-      "learning_rate": 4.949460916442048e-05,
-      "loss": 3.1119,
-      "step": 9750
-    },
-    {
-      "epoch": 13.14,
-      "eval_loss": 2.09057354927063,
-      "eval_runtime": 84.2266,
-      "eval_samples_per_second": 59.364,
-      "eval_steps_per_second": 0.938,
-      "step": 9750
-    },
-    {
-      "epoch": 14.15,
-      "learning_rate": 4.8989218328840976e-05,
-      "loss": 1.5021,
-      "step": 10500
-    },
-    {
-      "epoch": 14.15,
-      "eval_loss": 1.6629363298416138,
-      "eval_runtime": 83.9283,
-      "eval_samples_per_second": 59.575,
-      "eval_steps_per_second": 0.941,
-      "step": 10500
-    },
-    {
-      "epoch": 15.16,
-      "learning_rate": 4.84845013477089e-05,
-      "loss": 1.1682,
-      "step": 11250
-    },
-    {
-      "epoch": 15.16,
-      "eval_loss": 1.5476787090301514,
-      "eval_runtime": 83.9134,
-      "eval_samples_per_second": 59.585,
-      "eval_steps_per_second": 0.941,
-      "step": 11250
-    },
-    {
-      "epoch": 16.17,
-      "learning_rate": 4.7979110512129385e-05,
-      "loss": 0.9836,
-      "step": 12000
-    },
-    {
-      "epoch": 16.17,
-      "eval_loss": 1.5123697519302368,
-      "eval_runtime": 83.9374,
-      "eval_samples_per_second": 59.568,
-      "eval_steps_per_second": 0.941,
-      "step": 12000
-    },
-    {
-      "epoch": 17.18,
-      "learning_rate": 4.7474393530997306e-05,
-      "loss": 0.8542,
-      "step": 12750
-    },
-    {
-      "epoch": 17.18,
-      "eval_loss": 1.3803095817565918,
-      "eval_runtime": 83.8966,
-      "eval_samples_per_second": 59.597,
-      "eval_steps_per_second": 0.942,
-      "step": 12750
-    },
-    {
-      "epoch": 18.19,
-      "learning_rate": 4.696900269541779e-05,
-      "loss": 0.7554,
-      "step": 13500
-    },
-    {
-      "epoch": 18.19,
-      "eval_loss": 1.3329607248306274,
-      "eval_runtime": 83.8879,
-      "eval_samples_per_second": 59.603,
-      "eval_steps_per_second": 0.942,
-      "step": 13500
-    },
-    {
-      "epoch": 19.2,
-      "learning_rate": 4.949460916442048e-05,
-      "loss": 2.6984,
-      "step": 14250
-    },
-    {
-      "epoch": 19.2,
-      "eval_loss": 1.934728741645813,
-      "eval_runtime": 84.0312,
-      "eval_samples_per_second": 59.502,
-      "eval_steps_per_second": 0.94,
-      "step": 14250
-    },
-    {
-      "epoch": 20.21,
-      "learning_rate": 4.8989218328840976e-05,
-      "loss": 1.2723,
-      "step": 15000
-    },
-    {
-      "epoch": 20.21,
-      "eval_loss": 1.616538405418396,
-      "eval_runtime": 83.7157,
-      "eval_samples_per_second": 59.726,
-      "eval_steps_per_second": 0.944,
-      "step": 15000
-    },
-    {
-      "epoch": 21.23,
-      "learning_rate": 4.84845013477089e-05,
-      "loss": 1.002,
-      "step": 15750
-    },
-    {
-      "epoch": 21.23,
-      "eval_loss": 1.481406331062317,
-      "eval_runtime": 83.6915,
-      "eval_samples_per_second": 59.743,
-      "eval_steps_per_second": 0.944,
-      "step": 15750
-    },
-    {
-      "epoch": 22.24,
-      "learning_rate": 4.7979110512129385e-05,
-      "loss": 0.8449,
-      "step": 16500
-    },
-    {
-      "epoch": 22.24,
-      "eval_loss": 1.4224437475204468,
-      "eval_runtime": 83.7229,
-      "eval_samples_per_second": 59.721,
-      "eval_steps_per_second": 0.944,
-      "step": 16500
-    },
-    {
-      "epoch": 23.25,
-      "learning_rate": 4.7473719676549865e-05,
-      "loss": 0.7344,
-      "step": 17250
-    },
-    {
-      "epoch": 23.25,
-      "eval_loss": 1.3392431735992432,
-      "eval_runtime": 83.6972,
-      "eval_samples_per_second": 59.739,
-      "eval_steps_per_second": 0.944,
-      "step": 17250
-    },
-    {
-      "epoch": 24.26,
-      "learning_rate": 4.6969676549865234e-05,
-      "loss": 0.6533,
-      "step": 18000
-    },
-    {
-      "epoch": 24.26,
-      "eval_loss": 1.3550658226013184,
-      "eval_runtime": 83.7743,
-      "eval_samples_per_second": 59.684,
-      "eval_steps_per_second": 0.943,
-      "step": 18000
+      "epoch": 50.0,
+      "step": 50,
+      "total_flos": 32636710679400.0,
+      "train_loss": 0.2473917007446289,
+      "train_runtime": 8.5287,
+      "train_samples_per_second": 52.763,
+      "train_steps_per_second": 5.863
     }
   ],
   "logging_steps": 750,
-  "max_steps": 74200,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 100,
+  "num_train_epochs": 50,
   "save_steps": 750,
-  "total_flos": 7.79036533801943e+17,
+  "total_flos": 32636710679400.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a91c4ff3b80be24391e06650540dddea861285c3a8030b1771c2469cae3f40
+oid sha256:539f836c129844c7433ce90ce7a776a98d7e07cfa66853d433c5135b23816fc8
 size 4283